Search results

When you talk about a machine learning implementation, I assume it's a short term price prediction with a neural network. Just for establishing a situation where the question "filter or not" makes sense. Raw prices don't work well and complex filters, like a Kalman filter, don't work well...

Still, Easylanguage is slow as hell. I tested a small strategy that needed 4 seconds for a backtest in C. The same strategy needs 150 seconds on Multicharts in EasyLanguage. In favor of EasyLanguage, it's indeed much faster than R or Python.

R has a much larger user base than Matlab, and therefore also much more libraries for neural nets and other algos. For deep learning, look into DARCH, DEEPNET, and DNN.

Python is in fact a fine language, syntax-wise. Only problem is that it is just too slow for many programming tasks, that's why C++ is normally used for serious projects. A trading strategy in Python looks a bit nicer than the same strategy in C++, but runs 30 times slower. Not good for...

We call this kind of trading "Indicator Soup". Not meant deregatory; in our experience some of those systems indeed work, although most do not. As to the cost involved, and about how to work with a programmer, I've written a blog post here: http://www.financial-hacker.com/i-hired-a-contract-coder/

I'm in the system development business (I'm not fishing for a job here though). I only must smile about that permanent fear by beginners that programmers or other people "steal their system". Systems are a dime a dozen. I have my hard disk full of systems. If a programmer wanted to steal, he...

In fact hedge funds do not yet invest largely in AI research. They began hiring ML developers only recently. Most of their research still goes into conventional algorithms. ML for financial prediction bears two challenges, that's why other methods still prevail. First, whatever you predict, you...

Not to forget, the learning objective is also key. The return at the next bar is not always the best objective since it's strongly affected by noise. Better is a more distant prediction horizon, or something entirely different such as a Zigzag leg, or the presence or absence of a market...

No, we do not sell strategies. I also use that old "It can't work, otherwise you would trade it yourself and not sell it" argument sometimes, but in fact this statement is nonsense in most cases. We're paid for developing a system from client's specifications. He still owns it. We could not even...

In the medium two-digit range. But with many disclaimers. We program the systems for clients, so I can not provide details. Also we're doing this only for three years, and only since 2015 we got systems that really work. They're running live not yet long enough for determining solid performance...

60% failed, 40% work.

This seems to be the typical way of discussions on this forum: Someone utters an opinion, someone else disagrees, and the next argument is "you have no idea what you are talking about". I have indeed no idea where and what you have heard about machine learning. But I have developed more than 40...

This is a common misconception of how machine learning works. Why do you think all attempts to train a neural network with GO games failed over the last 20 years? And why did AlphaGo succeed? it had simply two differences to all previous attempts, a deeper network with more neurons, and a...

The algorithm is relatively irrelevant. Much more important are the data with which you feed it. Normally a bunch of indicators or other derivatives of the price curve. When you selected the features, then you can find the best algorithm for them. All of your list are available in R. You can...

Well... you can look first here for how to become a quant: http://www.turingfinance.com/how-to-be-a-quant/ and then here for how to develop a trading strategy: http://www.financial-hacker.com/build-better-strategies-part-3-the-development-process/ There are a million ways...

You need normally not pay for this, as sounding an alarm when the price crosses a limit is a very easy task in any automated system. It requires a minimum script, maybe 10 lines of code. In Zorro a simple version could look like this: int n = 0; while(asset(loop(Assets))) { if(priceClose(0)...

Partner up with fullautotrading. I believe he's still looking for someone buying his strategy and trading several million every minute with it.

With realistic trading costs, you would need about 90% win rate, or a similar reward/risk ratio for 1-minute scalping strategies. And there are also many other issues involved in trading on very short time frames: http://www.financial-hacker.com/is-scalping-irrational/ Better take stories from...

http://www.cftc.gov/opa/enf03/opa4789-03.htm

I have also implemented the API in C++. Technically the IB API is no challenge, in fact it was the easiest broker API that I've implemented so far. The problem is the very rudimentary information that IB delivers through the API, and that you have to find out many things by trial and error, for...